diff mbox series

drm/xe: Use write-back caching mode for system memory on DGFX

Message ID 20240619163904.2935-1-thomas.hellstrom@linux.intel.com (mailing list archive)
State New, archived
Headers show
Series drm/xe: Use write-back caching mode for system memory on DGFX | expand

Commit Message

Thomas Hellström June 19, 2024, 4:39 p.m. UTC
The caching mode for buffer objects with VRAM as a possible
placement was forced to write-combined, regardless of placement.

However, write-combined system memory is expensive to allocate and
even though it is pooled, the pool is expensive to shrink, since
it involves global CPU TLB flushes.

Moreover write-combined system memory from TTM is only reliably
available on x86 and DGFX doesn't have an x86 restriction.

So regardless of the cpu caching mode selected for a bo,
internally use write-back caching mode for system memory on DGFX.

Coherency is maintained, but user-space clients may perceive a
difference in cpu access speeds.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
Cc: Pallavi Mishra <pallavi.mishra@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: dri-devel@lists.freedesktop.org
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Effie Yu <effie.yu@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Jose Souza <jose.souza@intel.com>
Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
---
 drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
 drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
 include/uapi/drm/xe_drm.h        |  8 +++++-
 3 files changed, 37 insertions(+), 21 deletions(-)

Comments

Matthew Auld June 20, 2024, 9:03 a.m. UTC | #1
On 19/06/2024 17:39, Thomas Hellström wrote:
> The caching mode for buffer objects with VRAM as a possible
> placement was forced to write-combined, regardless of placement.
> 
> However, write-combined system memory is expensive to allocate and
> even though it is pooled, the pool is expensive to shrink, since
> it involves global CPU TLB flushes.
> 
> Moreover write-combined system memory from TTM is only reliably
> available on x86 and DGFX doesn't have an x86 restriction.
> 
> So regardless of the cpu caching mode selected for a bo,
> internally use write-back caching mode for system memory on DGFX.
> 
> Coherency is maintained, but user-space clients may perceive a
> difference in cpu access speeds.
> 
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
> Cc: Pallavi Mishra <pallavi.mishra@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Effie Yu <effie.yu@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> Cc: Jose Souza <jose.souza@intel.com>
> Cc: Michal Mrozek <michal.mrozek@intel.com>
> Cc: <stable@vger.kernel.org> # v6.8+
Acked-by: Matthew Auld <matthew.auld@intel.com>

> ---
>   drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
>   drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
>   include/uapi/drm/xe_drm.h        |  8 +++++-
>   3 files changed, 37 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 65c696966e96..31192d983d9e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -343,7 +343,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>   	struct xe_device *xe = xe_bo_device(bo);
>   	struct xe_ttm_tt *tt;
>   	unsigned long extra_pages;
> -	enum ttm_caching caching;
> +	enum ttm_caching caching = ttm_cached;
>   	int err;
>   
>   	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
> @@ -357,26 +357,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>   		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
>   					   PAGE_SIZE);
>   
> -	switch (bo->cpu_caching) {
> -	case DRM_XE_GEM_CPU_CACHING_WC:
> -		caching = ttm_write_combined;
> -		break;
> -	default:
> -		caching = ttm_cached;
> -		break;
> -	}
> -
> -	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> -
>   	/*
> -	 * Display scanout is always non-coherent with the CPU cache.
> -	 *
> -	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
> -	 * require a CPU:WC mapping.
> +	 * DGFX system memory is always WB / ttm_cached, since
> +	 * other caching modes are only supported on x86. DGFX
> +	 * GPU system memory accesses are always coherent with the
> +	 * CPU.
>   	 */
> -	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> -	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
> -		caching = ttm_write_combined;
> +	if (!IS_DGFX(xe)) {
> +		switch (bo->cpu_caching) {
> +		case DRM_XE_GEM_CPU_CACHING_WC:
> +			caching = ttm_write_combined;
> +			break;
> +		default:
> +			caching = ttm_cached;
> +			break;
> +		}
> +
> +		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> +
> +		/*
> +		 * Display scanout is always non-coherent with the CPU cache.
> +		 *
> +		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
> +		 * non-coherent and require a CPU:WC mapping.
> +		 */
> +		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> +		    (xe->info.graphics_verx100 >= 1270 &&
> +		     bo->flags & XE_BO_FLAG_PAGETABLE))
> +			caching = ttm_write_combined;
> +	}
>   
>   	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
>   		/*
> diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
> index 86422e113d39..10450f1fbbde 100644
> --- a/drivers/gpu/drm/xe/xe_bo_types.h
> +++ b/drivers/gpu/drm/xe/xe_bo_types.h
> @@ -66,7 +66,8 @@ struct xe_bo {
>   
>   	/**
>   	 * @cpu_caching: CPU caching mode. Currently only used for userspace
> -	 * objects.
> +	 * objects. Exceptions are system memory on DGFX, which is always
> +	 * WB.
>   	 */
>   	u16 cpu_caching;
>   
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 93e00be44b2d..1189b3044723 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -783,7 +783,13 @@ struct drm_xe_gem_create {
>   #define DRM_XE_GEM_CPU_CACHING_WC                      2
>   	/**
>   	 * @cpu_caching: The CPU caching mode to select for this object. If
> -	 * mmaping the object the mode selected here will also be used.
> +	 * mmaping the object the mode selected here will also be used. The
> +	 * exception is when mapping system memory (including evicted
> +	 * system memory) on discrete GPUs. The caching mode selected will
> +	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
> +	 * between GPU- and CPU is guaranteed. The caching mode of
> +	 * existing CPU-mappings will be updated transparently to
> +	 * user-space clients.
>   	 */
>   	__u16 cpu_caching;
>   	/** @pad: MBZ */
Matt Roper June 24, 2024, 9:37 p.m. UTC | #2
On Wed, Jun 19, 2024 at 06:39:04PM +0200, Thomas Hellström wrote:
> The caching mode for buffer objects with VRAM as a possible
> placement was forced to write-combined, regardless of placement.
> 
> However, write-combined system memory is expensive to allocate and
> even though it is pooled, the pool is expensive to shrink, since
> it involves global CPU TLB flushes.
> 
> Moreover write-combined system memory from TTM is only reliably
> available on x86 and DGFX doesn't have an x86 restriction.
> 
> So regardless of the cpu caching mode selected for a bo,
> internally use write-back caching mode for system memory on DGFX.
> 
> Coherency is maintained, but user-space clients may perceive a
> difference in cpu access speeds.
> 
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
> Cc: Pallavi Mishra <pallavi.mishra@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Effie Yu <effie.yu@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> Cc: Jose Souza <jose.souza@intel.com>
> Cc: Michal Mrozek <michal.mrozek@intel.com>
> Cc: <stable@vger.kernel.org> # v6.8+
> ---
>  drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
>  drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
>  include/uapi/drm/xe_drm.h        |  8 +++++-
>  3 files changed, 37 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 65c696966e96..31192d983d9e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -343,7 +343,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  	struct xe_device *xe = xe_bo_device(bo);
>  	struct xe_ttm_tt *tt;
>  	unsigned long extra_pages;
> -	enum ttm_caching caching;
> +	enum ttm_caching caching = ttm_cached;
>  	int err;
>  
>  	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
> @@ -357,26 +357,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
>  					   PAGE_SIZE);
>  
> -	switch (bo->cpu_caching) {
> -	case DRM_XE_GEM_CPU_CACHING_WC:
> -		caching = ttm_write_combined;
> -		break;
> -	default:
> -		caching = ttm_cached;
> -		break;
> -	}
> -
> -	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> -
>  	/*
> -	 * Display scanout is always non-coherent with the CPU cache.
> -	 *
> -	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
> -	 * require a CPU:WC mapping.
> +	 * DGFX system memory is always WB / ttm_cached, since
> +	 * other caching modes are only supported on x86. DGFX
> +	 * GPU system memory accesses are always coherent with the
> +	 * CPU.
>  	 */
> -	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> -	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
> -		caching = ttm_write_combined;
> +	if (!IS_DGFX(xe)) {
> +		switch (bo->cpu_caching) {
> +		case DRM_XE_GEM_CPU_CACHING_WC:
> +			caching = ttm_write_combined;
> +			break;
> +		default:
> +			caching = ttm_cached;
> +			break;
> +		}
> +
> +		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> +
> +		/*
> +		 * Display scanout is always non-coherent with the CPU cache.
> +		 *
> +		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
> +		 * non-coherent and require a CPU:WC mapping.
> +		 */
> +		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> +		    (xe->info.graphics_verx100 >= 1270 &&
> +		     bo->flags & XE_BO_FLAG_PAGETABLE))
> +			caching = ttm_write_combined;
> +	}
>  
>  	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
>  		/*
> diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
> index 86422e113d39..10450f1fbbde 100644
> --- a/drivers/gpu/drm/xe/xe_bo_types.h
> +++ b/drivers/gpu/drm/xe/xe_bo_types.h
> @@ -66,7 +66,8 @@ struct xe_bo {
>  
>  	/**
>  	 * @cpu_caching: CPU caching mode. Currently only used for userspace
> -	 * objects.
> +	 * objects. Exceptions are system memory on DGFX, which is always
> +	 * WB.
>  	 */
>  	u16 cpu_caching;
>  
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 93e00be44b2d..1189b3044723 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -783,7 +783,13 @@ struct drm_xe_gem_create {
>  #define DRM_XE_GEM_CPU_CACHING_WC                      2
>  	/**
>  	 * @cpu_caching: The CPU caching mode to select for this object. If
> -	 * mmaping the object the mode selected here will also be used.
> +	 * mmaping the object the mode selected here will also be used. The
> +	 * exception is when mapping system memory (including evicted
> +	 * system memory) on discrete GPUs. The caching mode selected will

Was this supposed to say "including evicted vram?"


Matt

> +	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
> +	 * between GPU- and CPU is guaranteed. The caching mode of
> +	 * existing CPU-mappings will be updated transparently to
> +	 * user-space clients.
>  	 */
>  	__u16 cpu_caching;
>  	/** @pad: MBZ */
> -- 
> 2.44.0
>
Souza, Jose July 2, 2024, 1:56 p.m. UTC | #3
On Wed, 2024-06-19 at 18:39 +0200, Thomas Hellström wrote:
> The caching mode for buffer objects with VRAM as a possible
> placement was forced to write-combined, regardless of placement.
> 
> However, write-combined system memory is expensive to allocate and
> even though it is pooled, the pool is expensive to shrink, since
> it involves global CPU TLB flushes.
> 
> Moreover write-combined system memory from TTM is only reliably
> available on x86 and DGFX doesn't have an x86 restriction.
> 
> So regardless of the cpu caching mode selected for a bo,
> internally use write-back caching mode for system memory on DGFX.
> 
> Coherency is maintained, but user-space clients may perceive a
> difference in cpu access speeds.

No regression on Mesa with this, so:

Acked-by: José Roberto de Souza <jose.souza@intel.com>

> 
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
> Cc: Pallavi Mishra <pallavi.mishra@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Effie Yu <effie.yu@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> Cc: Jose Souza <jose.souza@intel.com>
> Cc: Michal Mrozek <michal.mrozek@intel.com>
> Cc: <stable@vger.kernel.org> # v6.8+
> ---
>  drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
>  drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
>  include/uapi/drm/xe_drm.h        |  8 +++++-
>  3 files changed, 37 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 65c696966e96..31192d983d9e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -343,7 +343,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  	struct xe_device *xe = xe_bo_device(bo);
>  	struct xe_ttm_tt *tt;
>  	unsigned long extra_pages;
> -	enum ttm_caching caching;
> +	enum ttm_caching caching = ttm_cached;
>  	int err;
>  
>  	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
> @@ -357,26 +357,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
>  					   PAGE_SIZE);
>  
> -	switch (bo->cpu_caching) {
> -	case DRM_XE_GEM_CPU_CACHING_WC:
> -		caching = ttm_write_combined;
> -		break;
> -	default:
> -		caching = ttm_cached;
> -		break;
> -	}
> -
> -	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> -
>  	/*
> -	 * Display scanout is always non-coherent with the CPU cache.
> -	 *
> -	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
> -	 * require a CPU:WC mapping.
> +	 * DGFX system memory is always WB / ttm_cached, since
> +	 * other caching modes are only supported on x86. DGFX
> +	 * GPU system memory accesses are always coherent with the
> +	 * CPU.
>  	 */
> -	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> -	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
> -		caching = ttm_write_combined;
> +	if (!IS_DGFX(xe)) {
> +		switch (bo->cpu_caching) {
> +		case DRM_XE_GEM_CPU_CACHING_WC:
> +			caching = ttm_write_combined;
> +			break;
> +		default:
> +			caching = ttm_cached;
> +			break;
> +		}
> +
> +		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> +
> +		/*
> +		 * Display scanout is always non-coherent with the CPU cache.
> +		 *
> +		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
> +		 * non-coherent and require a CPU:WC mapping.
> +		 */
> +		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> +		    (xe->info.graphics_verx100 >= 1270 &&
> +		     bo->flags & XE_BO_FLAG_PAGETABLE))
> +			caching = ttm_write_combined;
> +	}
>  
>  	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
>  		/*
> diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
> index 86422e113d39..10450f1fbbde 100644
> --- a/drivers/gpu/drm/xe/xe_bo_types.h
> +++ b/drivers/gpu/drm/xe/xe_bo_types.h
> @@ -66,7 +66,8 @@ struct xe_bo {
>  
>  	/**
>  	 * @cpu_caching: CPU caching mode. Currently only used for userspace
> -	 * objects.
> +	 * objects. Exceptions are system memory on DGFX, which is always
> +	 * WB.
>  	 */
>  	u16 cpu_caching;
>  
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 93e00be44b2d..1189b3044723 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -783,7 +783,13 @@ struct drm_xe_gem_create {
>  #define DRM_XE_GEM_CPU_CACHING_WC                      2
>  	/**
>  	 * @cpu_caching: The CPU caching mode to select for this object. If
> -	 * mmaping the object the mode selected here will also be used.
> +	 * mmaping the object the mode selected here will also be used. The
> +	 * exception is when mapping system memory (including evicted
> +	 * system memory) on discrete GPUs. The caching mode selected will
> +	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
> +	 * between GPU- and CPU is guaranteed. The caching mode of
> +	 * existing CPU-mappings will be updated transparently to
> +	 * user-space clients.
>  	 */
>  	__u16 cpu_caching;
>  	/** @pad: MBZ */
Rodrigo Vivi July 2, 2024, 3:59 p.m. UTC | #4
On Wed, Jun 19, 2024 at 06:39:04PM +0200, Thomas Hellström wrote:
> The caching mode for buffer objects with VRAM as a possible
> placement was forced to write-combined, regardless of placement.
> 
> However, write-combined system memory is expensive to allocate and
> even though it is pooled, the pool is expensive to shrink, since
> it involves global CPU TLB flushes.
> 
> Moreover write-combined system memory from TTM is only reliably
> available on x86 and DGFX doesn't have an x86 restriction.
> 
> So regardless of the cpu caching mode selected for a bo,
> internally use write-back caching mode for system memory on DGFX.
> 
> Coherency is maintained, but user-space clients may perceive a
> difference in cpu access speeds.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

> 
> Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
> Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
> Cc: Pallavi Mishra <pallavi.mishra@intel.com>
> Cc: Matthew Auld <matthew.auld@intel.com>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
> Cc: Effie Yu <effie.yu@intel.com>
> Cc: Matthew Brost <matthew.brost@intel.com>
> Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
> Cc: Jose Souza <jose.souza@intel.com>
> Cc: Michal Mrozek <michal.mrozek@intel.com>
> Cc: <stable@vger.kernel.org> # v6.8+
> ---
>  drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
>  drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
>  include/uapi/drm/xe_drm.h        |  8 +++++-
>  3 files changed, 37 insertions(+), 21 deletions(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
> index 65c696966e96..31192d983d9e 100644
> --- a/drivers/gpu/drm/xe/xe_bo.c
> +++ b/drivers/gpu/drm/xe/xe_bo.c
> @@ -343,7 +343,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  	struct xe_device *xe = xe_bo_device(bo);
>  	struct xe_ttm_tt *tt;
>  	unsigned long extra_pages;
> -	enum ttm_caching caching;
> +	enum ttm_caching caching = ttm_cached;
>  	int err;
>  
>  	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
> @@ -357,26 +357,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
>  		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
>  					   PAGE_SIZE);
>  
> -	switch (bo->cpu_caching) {
> -	case DRM_XE_GEM_CPU_CACHING_WC:
> -		caching = ttm_write_combined;
> -		break;
> -	default:
> -		caching = ttm_cached;
> -		break;
> -	}
> -
> -	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> -
>  	/*
> -	 * Display scanout is always non-coherent with the CPU cache.
> -	 *
> -	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
> -	 * require a CPU:WC mapping.
> +	 * DGFX system memory is always WB / ttm_cached, since
> +	 * other caching modes are only supported on x86. DGFX
> +	 * GPU system memory accesses are always coherent with the
> +	 * CPU.
>  	 */
> -	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> -	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
> -		caching = ttm_write_combined;
> +	if (!IS_DGFX(xe)) {
> +		switch (bo->cpu_caching) {
> +		case DRM_XE_GEM_CPU_CACHING_WC:
> +			caching = ttm_write_combined;
> +			break;
> +		default:
> +			caching = ttm_cached;
> +			break;
> +		}
> +
> +		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
> +
> +		/*
> +		 * Display scanout is always non-coherent with the CPU cache.
> +		 *
> +		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
> +		 * non-coherent and require a CPU:WC mapping.
> +		 */
> +		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
> +		    (xe->info.graphics_verx100 >= 1270 &&
> +		     bo->flags & XE_BO_FLAG_PAGETABLE))
> +			caching = ttm_write_combined;
> +	}
>  
>  	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
>  		/*
> diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
> index 86422e113d39..10450f1fbbde 100644
> --- a/drivers/gpu/drm/xe/xe_bo_types.h
> +++ b/drivers/gpu/drm/xe/xe_bo_types.h
> @@ -66,7 +66,8 @@ struct xe_bo {
>  
>  	/**
>  	 * @cpu_caching: CPU caching mode. Currently only used for userspace
> -	 * objects.
> +	 * objects. Exceptions are system memory on DGFX, which is always
> +	 * WB.
>  	 */
>  	u16 cpu_caching;
>  
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index 93e00be44b2d..1189b3044723 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -783,7 +783,13 @@ struct drm_xe_gem_create {
>  #define DRM_XE_GEM_CPU_CACHING_WC                      2
>  	/**
>  	 * @cpu_caching: The CPU caching mode to select for this object. If
> -	 * mmaping the object the mode selected here will also be used.
> +	 * mmaping the object the mode selected here will also be used. The
> +	 * exception is when mapping system memory (including evicted
> +	 * system memory) on discrete GPUs. The caching mode selected will
> +	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
> +	 * between GPU- and CPU is guaranteed. The caching mode of
> +	 * existing CPU-mappings will be updated transparently to
> +	 * user-space clients.
>  	 */
>  	__u16 cpu_caching;
>  	/** @pad: MBZ */
> -- 
> 2.44.0
>
Mrozek, Michal July 4, 2024, 7:48 a.m. UTC | #5
The caching mode for buffer objects with VRAM as a possible placement was forced to write-combined, regardless of placement.

However, write-combined system memory is expensive to allocate and even though it is pooled, the pool is expensive to shrink, since it involves global CPU TLB flushes.

Moreover write-combined system memory from TTM is only reliably available on x86 and DGFX doesn't have an x86 restriction.

So regardless of the cpu caching mode selected for a bo, internally use write-back caching mode for system memory on DGFX.

Coherency is maintained, but user-space clients may perceive a difference in cpu access speeds.

Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Fixes: 622f709ca629 ("drm/xe/uapi: Add support for CPU caching mode")
Cc: Pallavi Mishra <pallavi.mishra@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: dri-devel@lists.freedesktop.org
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Effie Yu <effie.yu@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Jose Souza <jose.souza@intel.com>
Cc: Michal Mrozek <michal.mrozek@intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
---
 drivers/gpu/drm/xe/xe_bo.c       | 47 +++++++++++++++++++-------------
 drivers/gpu/drm/xe/xe_bo_types.h |  3 +-
 include/uapi/drm/xe_drm.h        |  8 +++++-
 3 files changed, 37 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c index 65c696966e96..31192d983d9e 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -343,7 +343,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 	struct xe_device *xe = xe_bo_device(bo);
 	struct xe_ttm_tt *tt;
 	unsigned long extra_pages;
-	enum ttm_caching caching;
+	enum ttm_caching caching = ttm_cached;
 	int err;
 
 	tt = kzalloc(sizeof(*tt), GFP_KERNEL); @@ -357,26 +357,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
 					   PAGE_SIZE);
 
-	switch (bo->cpu_caching) {
-	case DRM_XE_GEM_CPU_CACHING_WC:
-		caching = ttm_write_combined;
-		break;
-	default:
-		caching = ttm_cached;
-		break;
-	}
-
-	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
-
 	/*
-	 * Display scanout is always non-coherent with the CPU cache.
-	 *
-	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
-	 * require a CPU:WC mapping.
+	 * DGFX system memory is always WB / ttm_cached, since
+	 * other caching modes are only supported on x86. DGFX
+	 * GPU system memory accesses are always coherent with the
+	 * CPU.
 	 */
-	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
-	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
-		caching = ttm_write_combined;
+	if (!IS_DGFX(xe)) {
+		switch (bo->cpu_caching) {
+		case DRM_XE_GEM_CPU_CACHING_WC:
+			caching = ttm_write_combined;
+			break;
+		default:
+			caching = ttm_cached;
+			break;
+		}
+
+		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
+
+		/*
+		 * Display scanout is always non-coherent with the CPU cache.
+		 *
+		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
+		 * non-coherent and require a CPU:WC mapping.
+		 */
+		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
+		    (xe->info.graphics_verx100 >= 1270 &&
+		     bo->flags & XE_BO_FLAG_PAGETABLE))
+			caching = ttm_write_combined;
+	}
 
 	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
 		/*
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 86422e113d39..10450f1fbbde 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -66,7 +66,8 @@ struct xe_bo {
 
 	/**
 	 * @cpu_caching: CPU caching mode. Currently only used for userspace
-	 * objects.
+	 * objects. Exceptions are system memory on DGFX, which is always
+	 * WB.
 	 */
 	u16 cpu_caching;
 
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 93e00be44b2d..1189b3044723 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -783,7 +783,13 @@ struct drm_xe_gem_create {
 #define DRM_XE_GEM_CPU_CACHING_WC                      2
 	/**
 	 * @cpu_caching: The CPU caching mode to select for this object. If
-	 * mmaping the object the mode selected here will also be used.
+	 * mmaping the object the mode selected here will also be used. The
+	 * exception is when mapping system memory (including evicted
+	 * system memory) on discrete GPUs. The caching mode selected will
+	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
+	 * between GPU- and CPU is guaranteed. The caching mode of
+	 * existing CPU-mappings will be updated transparently to
+	 * user-space clients.
 	 */
 	__u16 cpu_caching;
 	/** @pad: MBZ */
--
2.44.0

Acked-by: Michal Mrozek <michal.mrozek@intel.com>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
index 65c696966e96..31192d983d9e 100644
--- a/drivers/gpu/drm/xe/xe_bo.c
+++ b/drivers/gpu/drm/xe/xe_bo.c
@@ -343,7 +343,7 @@  static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 	struct xe_device *xe = xe_bo_device(bo);
 	struct xe_ttm_tt *tt;
 	unsigned long extra_pages;
-	enum ttm_caching caching;
+	enum ttm_caching caching = ttm_cached;
 	int err;
 
 	tt = kzalloc(sizeof(*tt), GFP_KERNEL);
@@ -357,26 +357,35 @@  static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
 		extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
 					   PAGE_SIZE);
 
-	switch (bo->cpu_caching) {
-	case DRM_XE_GEM_CPU_CACHING_WC:
-		caching = ttm_write_combined;
-		break;
-	default:
-		caching = ttm_cached;
-		break;
-	}
-
-	WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
-
 	/*
-	 * Display scanout is always non-coherent with the CPU cache.
-	 *
-	 * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
-	 * require a CPU:WC mapping.
+	 * DGFX system memory is always WB / ttm_cached, since
+	 * other caching modes are only supported on x86. DGFX
+	 * GPU system memory accesses are always coherent with the
+	 * CPU.
 	 */
-	if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
-	    (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
-		caching = ttm_write_combined;
+	if (!IS_DGFX(xe)) {
+		switch (bo->cpu_caching) {
+		case DRM_XE_GEM_CPU_CACHING_WC:
+			caching = ttm_write_combined;
+			break;
+		default:
+			caching = ttm_cached;
+			break;
+		}
+
+		WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
+
+		/*
+		 * Display scanout is always non-coherent with the CPU cache.
+		 *
+		 * For Xe_LPG and beyond, PPGTT PTE lookups are also
+		 * non-coherent and require a CPU:WC mapping.
+		 */
+		if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
+		    (xe->info.graphics_verx100 >= 1270 &&
+		     bo->flags & XE_BO_FLAG_PAGETABLE))
+			caching = ttm_write_combined;
+	}
 
 	if (bo->flags & XE_BO_FLAG_NEEDS_UC) {
 		/*
diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
index 86422e113d39..10450f1fbbde 100644
--- a/drivers/gpu/drm/xe/xe_bo_types.h
+++ b/drivers/gpu/drm/xe/xe_bo_types.h
@@ -66,7 +66,8 @@  struct xe_bo {
 
 	/**
 	 * @cpu_caching: CPU caching mode. Currently only used for userspace
-	 * objects.
+	 * objects. Exceptions are system memory on DGFX, which is always
+	 * WB.
 	 */
 	u16 cpu_caching;
 
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 93e00be44b2d..1189b3044723 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -783,7 +783,13 @@  struct drm_xe_gem_create {
 #define DRM_XE_GEM_CPU_CACHING_WC                      2
 	/**
 	 * @cpu_caching: The CPU caching mode to select for this object. If
-	 * mmaping the object the mode selected here will also be used.
+	 * mmaping the object the mode selected here will also be used. The
+	 * exception is when mapping system memory (including evicted
+	 * system memory) on discrete GPUs. The caching mode selected will
+	 * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
+	 * between GPU- and CPU is guaranteed. The caching mode of
+	 * existing CPU-mappings will be updated transparently to
+	 * user-space clients.
 	 */
 	__u16 cpu_caching;
 	/** @pad: MBZ */